Rin Arakaki

Product Manager, Technical Lead, Voice Team, Algoage

Nov 2025 — Current, Tokyo, Japan

Real-time AI copilot for contact-centre operators — telephony, transcription, knowledge and topic detection as one system on the customer's own stack.

• Founded a real-time AI copilot for contact-centre operators and led it from first commit to multi-tenant production in nine months, now running across seven customers.
• Grounded the product in observed practice — spent time on-site at a customer's contact centre learning how operators actually work, and ran user interviews to test the product hypothesis before committing to a roadmap.
• Owned the architecture across telephony integration, real-time voice, AI agent, multi-tenant backend, browser client and infrastructure, with service contracts defined before implementation and business rules held as data rather than code.
• Designed the dimension model the product organises itself around — a customer's own classification axes, resolved by one embedding-based lookup serving both knowledge management and live topic detection.
• Made knowledge search grounded by construction — doc2query expansion generating each document's answerable queries, verified offline, so an operator is never offered a search that returns nothing and the serve path does no retrieval at all.
• Closed the knowledge loop — operator flags, usage signals and post-call AI gap detection converging on one queue, with edits authored and approved separately and published live to the next call.
• Built the platform that measures whether the AI is any good — eleven dimensions scored against synthetic calls driven through the real telephony path, with operator accept-versus-edit rate as ground truth.
• Identified a recurring reliability failure class the team had been patching case by case, and replaced six rounds of defensive fixes with a single design invariant.
• Established reliability as a governed practice: service-level objectives owned as code, burn-rate alerting, and an error-budget policy binding budget exhaustion to a deploy freeze.
• Grew the team from two to fourteen — five engineers, three project managers, an engineering manager, three QA and a designer — and defined a new Product Ops function after recognising work chartered as project management as a structurally different role.
• Won seven customers on product strength — exhibition demand, and a vendor referring its own customers after evaluating the copilot — with integration breadth across their existing stacks carrying as much of the value as the AI.
• Built the agent-operated pipeline — executable specifications, automated code review, documentation reconciliation — that produced and maintains a million-line codebase without a line hand-written, with correctness held by invariant tests that fail the build and a test suite a third the size of the application code.

Technologies — Amazon Connect, Twilio, LiveKit, WebRTC, Deepgram, Cartesia, Anthropic Claude, OpenAI, Gemini, Chrome Extension, Model Context Protocol, Spec Kit, Temporal, OpenTelemetry, pgvector, Amazon Web Services, Terraform

Software Engineer, Part-Time, Archemis

Oct 2025 — Current, Tokyo, Japan

AI-native crypto trading hedge fund.

• Owned a live trading strategy end to end in Rust — six macro-economic indicators resolved into a correlation-weighted signal sizing a Bitcoin futures position — through to production deployment.
• Wrote the trading logic and data-validation specifications, then the input validation they define — non-finite values, negative yields, market-holiday gaps, insufficient history.
• Specified the next strategy before implementing it — auditing the analyst's definition and documenting its contradictions, with every threshold stated as inclusive or exclusive.

Technologies — Rust, Google Cloud Platform, Kubernetes, Terraform

Software Engineer, aisaac

Jul 2025 — Nov 2025, Tokyo, Japan

Dating app for over-40s in Japan.

• Architected and implemented web payments end to end — cross-platform authentication, subscription lifecycle, user-behaviour tracking, purchase event logs, refunds and coupons, and a double-charge race fix — improving ROAS by 30%.
• Built revenue forecasting over the transactional data to support business planning.
• Researched and designed a new matching algorithm combining TF-IDF and vector calculation.

Technologies — SQL, TypeScript, Google Cloud Platform, React Native, Google Analytics, Adjust

Forward Deployed Engineer, JAPAN AI

Apr 2025 — Jun 2025, Tokyo, Japan

Customer deployments of the AI call centre product.

• Worked weekly with a call-centre client to elicit data, constraints and objectives, then formulated and shipped a constraint-programming agent matching operators to customer segments to maximise expected conversions under shift constraints.

Technologies — OR-Tools, C++, Python, Google Cloud Platform

Full-Stack Engineer, Speech Team, JAPAN AI

Oct 2024 — Apr 2025, Tokyo, Japan

LLM and generative AI research and development.

• Took ownership of an experimental real-time voice AI platform, leading it through inbound and outbound call-centre PoCs with three customers and into an official product.
• Researched UDP-based SIP and RTP protocols and Kubernetes networking to understand the failure modes of stateful voice workloads, then migrated the prototype onto LiveKit Agents and redesigned the boundary between the agent runtime and control plane.

Technologies — LiveKit, Twilio, SIP, WebRTC, Whisper, Kubernetes, gRPC, Python, Google Cloud Platform, RunPod

Full-Stack Engineer, Kakeai

Sep 2023 — Sep 2024, Tokyo, Japan

One-on-one meeting platform with real-time AI transcription and summarisation.

• Rebuilt the core calendar platform around a unified event and recurrence model, cutting its implementation from ~22K to ~7K lines while expanding its capabilities from advanced scheduling to enterprise mentor-mentee pairing with a stable matching algorithm.
• Analysed six quarterly survey waves and 7,400 one-on-one records to test whether platform adoption improved employee engagement; found a +1.96-point association but no dose-response effect, and designed propensity-score-matching and difference-in-differences analyses to separate adoption from selection.

Technologies — Python, TypeScript, Amazon Web Services, Terraform, Ruby on Rails

Lead Data Engineer, Viagate

Apr 2023 — Aug 2023, Tokyo, Japan

Marketing research platform using eye tracking and facial expression recognition.

• Anticipated that the pre-existing relational architecture would not scale for high-volume eye-tracking data and prepared a columnar alternative in parallel with the iOS engineer; when production proved the prediction, led the switch, and the prepared architecture carried the workload reliably.
• Built the data platform behind an advertising research product, aligning eye-tracking and facial-expression signals with video and web content, and added audience segmentation so clients could target research participants and compare responses across segments.

Technologies — OpenCV, Apache Arrow/Parquet, Protocol Buffers, PostgreSQL, Python, Amazon Web Services

Technical Lead, Operations Lead, Delipicks

Jun 2019 — May 2020, Tokyo, Japan

B2B food delivery startup; joined 6 months after launch.

• Led both technology and daily operations, working alongside the CEO to design business processes, software and operating procedures concurrently; ran over ten user interviews and took part in UX workshops to design the operator experience from first-hand use of the service.
• Recognised that menu selection and delivery routing had to be solved jointly to scale the business; formulated a revenue-maximisation problem balancing restaurant capacity and weekly menu variety against a 30-minute delivery constraint, then introduced combinatorial optimisation to replace manual planning.
• Built and managed the engineering team around the business's evolving technical needs, recruiting two engineers and the mathematical-optimisation specialist needed to take the planning approach into production.
• Worked directly across both sides of the marketplace with the CEO — from acquiring corporate customers to opening restaurant partnerships and deploying into supplier operations — then used sales and operational data to negotiate commercial terms, helping achieve positive unit economics.

Technologies — OR-Tools, Firebase, Python, JavaScript, Google Cloud Platform

Software Engineer, Styler

Aug 2018 — Mar 2019, Tokyo, Japan

Fashion retail platform bridging online and in-store experience (OMO — online-merge-offline).

• Planned the architectural transition to rapidly launch a new owned-media product alongside the existing Rails monolith; led the transition and product delivery, including metadata-based product discovery that improved on-site search and SEO.
• Helped build a six-nationality engineering team as development moved in-house from offshore, bridging the English-speaking engineers with Japanese product and business teams and establishing direct collaboration and shared ownership of release quality.

Technologies — Kubernetes, Python, Google Cloud Platform, Ruby on Rails

Software Engineer, MarketEnterprise

Apr 2016 — Dec 2017, Tokyo, Japan

Resale and rental business with complex internal operations.

• As the only engineer among more than fifteen new graduates in the on-the-job training programme, spent three months embedded across sales and fulfilment operations — from call-centre purchasing, photography and listing to logistics — to understand the workflows first-hand and design the internal systems around them.
• Modernised the legacy platform by designing and implementing the organisation-wide fine-grained access control API, establishing the foundation for the company's transition to microservices; resolved a stalled performance issue by reducing authorisation latency from 7 seconds to 0.2 seconds.

Technologies — MySQL, Python, JavaScript, Amazon Web Services

The Open University of Japan, Bachelor's Degree, Liberal Arts

Apr 2012 — Mar 2016, Tokyo, Japan

• Completed degree requirements in 2 years.

Founder, Synthetic

Dec 2020 — Present, Tokyo, Japan

Independent research initiative — formal AI reasoning and automated proof generation. Self-funded and self-directed since 2020; sustained across 5,000+ commits.

• Designing a graph and network-based search and indexing system for mathematical formulae, applied to automated theorem discovery.
• Investigating the theorem provers — Lean, Coq, Isabelle — and their proof search engines.
• Researching formal proof generation through LLM and reinforcement-learning feedback loops.

Technologies — Rust, Python, TypeScript